© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99669
    Prev
    Next
    INDEX
    Explanations

    H2O or H2O2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_14_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ים
    0.54
    Gosudarstvennyj
    0.52
    స
    0.50
    وك
    0.50
    ၢ
    0.50
    ():
    0.50
     dvou
    0.50
    後
    0.49
    ЕМ
    0.49
    _:
    0.49
    POSITIVE LOGITS
    ald
    0.59
    te
    0.57
    live
    0.57
    idle
    0.56
    are
    0.54
    ho
    0.54
    he
    0.54
    bout
    0.54
    teacher
    0.53
    t
    0.53
    Activations Density 0.003%

    No Known Activations